mcpField
N
neo-clarification

neo-clarification

github.com/benknightdark開発735 回インストール4 日前に更新
リポジトリ

neo-clarification について

neo-clarificationは、ユーザーの苦情、スクリーンショット、ログを構造化された要件に変換する仕様です。事実の抽出、5W1H分析、確認質問の作成を経て、繁体字中国語のレポートを作成します。

主な機能

  1. 01観察事実と期待の切り分け
  2. 02システム境界と5W1Hによる分析
  3. 03不足情報と確認質問の特定
  4. 04構造化された繁体字中国語レポートの生成
  5. 05レポート構成と質問数の確認

活用シーン

  1. 01不具合の申告を要件に整理
  2. 02スクリーンショットやログの挙動を確認
  3. 03開発者向けの構造化された引き継ぎを準備

インストール

コマンドをコピーしてターミナルで実行します。

$npx skills add https://github.com/benknightdark/neo-skills --skill neo-clarification

インストール後、Claude Code で/neo-clarificationを入力して読み込まれたか確認します。

同梱ファイル

SKILL.md と一緒にインストールされる参考資料やスクリプト。

assets/
clarification-template.md
evals/
eval_queries.json
evals.json
references/
5w1h-framework.md
scripts/
validate-requirements.py

README（原文）English

プロジェクトの README より

この README の日本語訳はまだありません。以下は英語の原文です。日本語の紹介はページ上部をご覧ください。

Requirement Clarification Specifications

Apply the Inversion & Generator Pattern. Follow this protocol strictly to translate raw, chaotic user complaints and screenshots into clean, structured system specifications.

1. Perceive Phase

  1. Information Extraction:

    • Carefully read the user's text and inspect any attached screenshots or logs.
    • Filter out emotional noise, frustrations, and blame.
    • Separate objective facts (what is currently happening or visible) from user expectations (what they wanted to accomplish).

  2. Identify System Boundaries:

    • Determine the scope, domain, and potential technical layers affected by the feedback (e.g., frontend rendering, network APIs, database states, permission groups).

2. Reason Phase

  1. Load Analysis Framework:

    • Always read the external analysis guide before starting your deduction: 5w1h-framework.md

  2. Context Reconstruction (5W1H):

    • Map the extracted facts to the 5W1H framework (Who, Where, When, What, Why, How).
    • Formulate logical hypotheses on the root causes of UI anomalies or system behaviors.

  3. Identify Gaps:

    • Pinpoint critical missing information (e.g., browser environment, specific action steps, parameters, error logs).
    • Prepare a list of clarifying questions to ask the user.

3. Act Phase

Generate a structured "Requirement Translation and Clarification Report" strictly in Traditional Chinese (Taiwan). Follow these steps:

  1. Load Output Template:

  2. Compile the Report:

    • Fill in the template using Traditional Chinese.
    • Context Restoration: Present objective facts concisely without emotional adjectives.
    • User Story: Use the strict format: "身為... 我想要... 以便於..."
    • System Requirements & Hypotheses: Highlight key rendering, API, and validation checkpoints for the development team.
    • Open Questions: List between 2 and 10 polite, precise, and constructive clarifying questions.

  3. Self-Validation:

    • Proactively validate your report using the non-interactive python script: 
      uv run skills/neo-clarification/scripts/validate-requirements.py -i <path_to_saved_report>
      (Or verify mentally that all sections exist and the number of questions is between 2 and 10 before final output).

4. Communication Guidelines

  • Maintain Empathetic Neutrality: Acknowledge the user's difficulty, but never agree that the system is "broken" or "a disaster" in the official report. Use neutral, objective descriptions.
  • Strictly No Guesswork: Do NOT invent features that the user did not hint at. Ask clarifying questions instead.

コメント

Markdown 対応